Yixin Zhang, Tong Zhou, Zhewen Ding, Yanqing Lu, Xuping Zhang, Feng Wang, Ningmu Zou. Classification of interference-fading tolerant Φ-OTDR signal using optimal peak-seeking and machine learning [Invited][J]. Chinese Optics Letters, 2021, 19(3): 030601
- Chinese Optics Letters
- Vol. 19, Issue 3, 030601 (2021)
Fig. 1. Flow chart of fading suppression method.
Fig. 2. (a) Probability of signal falling into the dead zone under different window size (100 ns). (b) Probability of signal falling into the dead zone under different pulse width.
Fig. 3. (a) Ada-5032E. (b) Schematic diagram of the experiment. (NLL, narrow-linewidth laser; AOM, acoustic-optical modulator; FUT, fiber under test; EDFA, erbium-doped fiber amplifier; Cir, circulator; BPD, balanced photodetector; DAQ, data acquisition card; PZT, piezo transducer.)
Fig. 4. STFT spectrum of phase results in 15 s. (a) Traditional method. (b) Proposed method.
Fig. 5. Accuracy of two methods within 5 min.
Fig. 6. STFT spectrum of 10 ramming ground tests. (a) Traditional method. (b) Proposed method.
Fig. 7. (a) Excavator digging event. (b) Time domain wave pattern of an invasive event. (c) Frequency-domain image after STFT. (d) Binary image after threshold filtering.
Fig. 8. (a) Parameter optimization results of SVM model. (b) Schematic structure of feedforward neural network. (c) Mean squared error.
|
Table 1. Definition of Pattern Features
|
Table 2. Category and Counts of Samples and Labels
| ||||||||||||||||||||||||||
Table 3. Testing Dataset and Results of Both Models
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20